Chizat, Lénaïc
- Statistical and Topological Properties of Sliced Probability Divergences
2020/03/12 by Nadjahi, Kimia, Durmus, Alain, Chizat, Lénaïc +3 · 8 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Mean-Field Langevin Dynamics: Exponential Convergence and Annealing
2022/02/02 by Chizat, Lénaïc · 6 citations
#FOS: Mathematics #Optimization and Control (math.OC)
- Infinite-width limit of deep linear neural networks
2022/11/29 by Chizat, Lénaïc, Colombo, Maria, Fernández-Real, Xavier +1 · 4 citations
#35Q49 #68T07 #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport
2017/11/06 by Alexis Thibault, Thibault, Alexis, Lénaïc Chizat +5 · 2 citations
Computer Science · Engineering · Mathematics · #Advanced Optimization Algorithms Research #FOS: Mathematics #Numerical Analysis (math.NA) #Optimization and Control (math.OC) #Optimization and Variational Analysis #Spacecraft Dynamics and Control
- Deep linear networks for regression are implicitly regularized towards flat minima
2024/05/22 by Pierre Marion, Lénaïc Chizat, Marion, Pierre +1 · 5 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications
- Displacement smoothness of entropic optimal transport
2022/10/01 by Guillaume Carlier, Lénaïc Chizat, Carlier, Guillaume +3 · 3 citations
Mathematics · #35A15 #49K40 #49Q22 #Analysis of PDEs (math.AP) #FOS: Mathematics #Geometric Analysis and Curvature Flows #Optimization and Control (math.OC)
- The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
2023/11/30 by Lénaïc Chizat, Chizat, Lénaïc, Praneeth Netrapalli +1 · 4 citations
Computer Science · Physics and Astronomy · #68T07 #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Model Reduction and Neural Networks #Neural Networks and Applications
- Trajectory Inference via Mean-field Langevin in Path Space
2022/05/14 by Chizat, Lénaïc, Zhang, Stephen, Heitz, Matthieu +1 · 2 citations
#90-08 (Primary) 62M99 (Secondary) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Sharper Exponential Convergence Rates for Sinkhorn's Algorithm in Continuous Settings
2024/07/01 by Lénaïc Chizat, Chizat, Lénaïc, Alex Delalande +3 · 2 citations
Computer Science · Engineering · #Advanced Numerical Analysis Techniques #Computability, Logic, AI Algorithms #FOS: Mathematics #Optimization and Control (math.OC) #Stochastic Gradient Optimization Techniques
- Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit
2021/10/29 by Hajjar, Karl, Chizat, Lénaïc, Giraud, Christophe · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
2024/06/24 by Guillaume Wang, Alireza Mousavi-Hosseini, Wang, Guillaume +3 · 2 citations
Mathematics · Physics and Astronomy · #Advanced Thermodynamics and Statistical Mechanics #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Mathematical Biology Tumor Growth #Optimization and Control (math.OC)
- An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games
2022/11/02 by Wang, Guillaume, Chizat, Lénaïc · 1 citation
#Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC)
- Annealed Sinkhorn for Optimal Transport: convergence, regularization path and debiasing
2024/08/21 by Chizat, Lénaïc · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC)